ChatBedrockConverse._converse_params() Rejects strict Parameter

[bharath-arcot-babu]

Package

langchain-aws

Checked other resources

• I added a descriptive title to this issue
• I searched the LangChain documentation with the integrated search
• I used the GitHub search to find a similar issue and didn't find it
• I am sure this is a bug and not a question or request for help

Example Code

from langchain_aws import ChatBedrockConverse
from langgraph.prebuilt import create_react_agent
from langchain.tools import tool

@tool
def example_tool(query: str) -> str:
    """Example tool."""
    return f"Result for {query}"

model = ChatBedrockConverse(
    model_id="anthropic.claude-3-5-sonnet-20240620-v1:0",
    region_name="us-east-1"
)

agent = create_react_agent(model, [example_tool])

# Trigger the error with streaming
async def test():
    async for event in agent.astream_events(
        {"messages": [{"role": "user", "content": "test"}]},
        config={"run_name": "test"}
    ):
        print(event)

# Run and get: TypeError: ChatBedrockConverse._converse_params() got an unexpected keyword argument 'strict'

Error Message and Stack Trace (if applicable)

Description

Summary
ChatBedrockConverse from langchain-aws 1.0.3 fails during agent streaming with a TypeError when LangChain-core attempts to pass the strict parameter for structured output support.

Error
TypeError: ChatBedrockConverse._converse_params() got an unexpected keyword argument 'strict'
Full Traceback Context:

Triggered during: astream_events() on an agent with ChatBedrockConverse as the LLM
Call path: langchain_aws/chat_models/bedrock_converse.py, line 923 in _stream() → _converse_params()
Root cause: _converse_params() method signature doesn't include **kwargs to accept strict parameter
Affected Versions
Package: langchain-aws 1.0.3 (and likely earlier 1.0.x versions)
Triggered by: langchain-core ≥ 0.3.0 with structured output support
Environment: Python 3.12, async streaming context

[michaelnchin]

Confirmed that the code sample works with the update in #882.